CN109157202A - A kind of cardiovascular disease early warning system based on more physiological signal depth integrations - Google Patents
A kind of cardiovascular disease early warning system based on more physiological signal depth integrations Download PDFInfo
- Publication number
- CN109157202A CN109157202A CN201811085130.4A CN201811085130A CN109157202A CN 109157202 A CN109157202 A CN 109157202A CN 201811085130 A CN201811085130 A CN 201811085130A CN 109157202 A CN109157202 A CN 109157202A
- Authority
- CN
- China
- Prior art keywords
- signal
- physiological
- module
- frequency
- physiological signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/681—Wristwatch-type devices
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6824—Arm or wrist
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
Abstract
The present invention provides the cardiovascular disease early warning system based on more physiological signal depth integrations, is related to wearable health medical treatment monitoring technical field.The system includes wearable device, more physiology signal acquisition devices, transmitting device, intelligent terminal and cloud server；More physiology signal acquisition devices and transmitting device are arranged on wearable device；The physiological signal data of acquisition is simultaneously transferred to intelligent terminal by transmitting device by the physiological signal of more physiology signal acquisition device acquisition detected persons；Intelligent terminal plug-in, judges whether detected person has risk of cardiovascular diseases, and the physiological signal of processing is sent to cloud server；The cloud server plug-in carries out classification of diseases and diagnosis to more physiological signals of wearer, and feeds back to intelligent terminal；Cardiovascular disease early warning system provided by the invention based on more physiological signal depth integrations, provides more accurate reference for the assessment of cardiac function and the diagnosis of heart disease.
Description
Technical field
The present invention relates to wearable health medical treatment monitoring technical fields, more particularly to one kind to be melted based on more physiological signal depth
The cardiovascular disease early warning system of conjunction.
Background technique
Cardiovascular disease has become a kind of very universal disease, seriously threatens the health of the mankind.However, in China
Under the overall background that medical resource is relatively deficient, aging aggravates, intelligent, personalized diagnostic medical modality possesses huge hair
Exhibition prospect.Future, the wearable health care settings that can merge multi-physiological-parameter will become the main force of digitlization portable medical
Army.
In numerous physiological signals, electrocardiosignal be detect heart disease important means, especially have it is sudden and
The cardiovascular disease of randomness.And the information of form, intensity and rate that pulse wave shows etc., reflection human body are cardiovascular
The important physiological and pathological information of system.Electrocardio and pulse signal belong to small-signal, and amplitude is low, and frequency is low, so extracting the heart
During arteries and veins signal, it is highly prone to various interference.
The patent of invention of Patent No. 201710169969.5 proposes a kind of electrocardiograph monitoring device based on electronics epidermis,
Heart rate, electrocardio are detected, and carries out signal processing and transmission.Above-mentioned patent all start with from measurement electrocardio, hrv parameter provide body-building,
Medical reference scheme.However, being not carried out multi-channal physiological combined monitoring and ginseng under the premise of obtaining accurate electrocardiosignal
Examine, and according to the detection of the multi-physiological-parameter of different patients and ECG Signal Analysis, carry out depth integration, thus to disease into
Row recurrence sieving and diagnosis and personalized risk of cardiovascular diseases early warning；The patent of invention of Patent No. 201510873447.4 proposes
A kind of bio-signal acquisition system based on multichannel flexible fusion solves multichannel binary and detects existing conflicting letter
The patent of invention of breath fusion problem and Patent No. 201680078461.8 proposes a kind of physiological parameter signals fusion treatment
Method, apparatus and system solve the joint judgment mechanism between a variety of physiological parameters, this two patents exist primarily directed to doctor
During more physiological signal Combining diagnosis, aid decision scheme is provided for diagnosis, but without providing real-time disease
Diagnosis and early warning result.
Summary of the invention
It is a kind of based on more physiological signals the technical problem to be solved by the present invention is in view of the above shortcomings of the prior art, provide
The cardiovascular disease early warning system of depth integration is realized and carries out early warning to risk of cardiovascular diseases.
A kind of cardiovascular disease early warning system based on more physiological signal depth integrations, including wearable device, more physiology letter
Number acquisition device, transmitting device, intelligent terminal and cloud server；The wearable device is worn on detected person's wrist
Portion, more physiology signal acquisition devices and transmitting device are arranged on wearable device；More physiology signal acquisition devices
For acquiring the physiological signal of detected person；The transmitting device is used for the physiological signal for acquiring more physiology signal acquisition devices
Data are transferred to intelligent terminal；The intelligent terminal plug-in, for carrying out the physiological signal of detected person
Processing, judges whether the detected person has risk of cardiovascular diseases, carries out disease risks early warning, assists diagnosis, and will place
The physiological signal of reason is sent to cloud server；The cloud server plug-in, the disease based on deep learning are intelligently divided
Class method carries out classification of diseases and diagnosis according to more physiological signals of the kinds of Diseases of trained mistake to wearer, and will knot
Fruit feeds back to intelligent terminal；
Program built in the intelligent terminal include signal intelligent pretreatment unit, feature extraction unit and parameter calculate with
Analytical unit and Risk-warning unit；The signal intelligent pretreatment unit realization acquires more physiology signal acquisition devices more
Physiological signal is pre-processed, and pretreated more physiological signals are transferred to cloud server；The feature extraction unit pair
Feature point extraction is carried out by a variety of physiological signal waveforms of pretreated human body；It includes time domain that the parameter, which is calculated with analytical unit,
Parameter calculates and analysis module and frequency domain parameter calculating and analysis module；The time domain parameter is calculated with analysis module according to mostly raw
Reason signal characteristic abstraction is as a result, the time domain parameter for carrying out each physiological signal calculates and analysis；The frequency domain parameter calculates and analysis
Module carries out frequency domain parameter according to the time frequency analysis result of more physiological signals and calculates and analyze, the amplitude-frequency after seeking its Fourier transformation
Characteristic；The Risk-warning unit is anti-according to the real-time time-frequency domain analysis results of a variety of physiological signal parameters and cloud server
Feedback assists diagnosis as a result, progress risk of cardiovascular diseases early warning；
Program built in the cloud server includes the depth of multi-path time frequency analysis unit and the fusion of more physiological signals
Analytical calculation unit；The multi-path time frequency analysis unit includes time-domain analysis module and frequency-domain analysis module；The time domain point
Analysis module carries out identical mapping respectively to collected more physiological signal datas and down-sampling converts, more after obtaining identical mapping
Physiological signal data generates the time series sketch of different time scales, using down-sampling transformation thus to obtain multiple and different
The input time sequence of down-sampling rate；The frequency-domain analysis module, which uses collected more physiological signal datas, has multiple put down
The low-frequency filter removal High-frequency Interference and random noise of slippery, the rolling average of different windows is utilized according to different smoothnesses,
Obtain the input time sequence of multi-frequency；The depth analysis computing unit of the more physiological signals fusion is by multi-path time frequency analysis
The result that unit obtains, which is input in convolutional neural networks, carries out convolution algorithm；Letter is carried out in full articulamentum or other classifiers
Breath summarizes, and obtains classification results；Finally, the different cardiovascular diseases that more physiological signal measurements data of wearer are obtained from training
The aspect ratio pair of disease, obtains risk of cardiovascular diseases classification results, and result is fed back to intelligent terminal.
Preferably, the wearable device includes elastic wristband, shell and dial plate；The elastic wristband by tender texture material
Material is made, and middle position is two buttons on the outside of elastic wristband；Dial plate is installed in the outside of elastic wristband, and elastic wristband both ends are to use
In the velcro of fixed elastic wristband；The shell is installed on outside dial plate, index dial structure is formed, for encapsulating hardware circuit；
Buckle is installed at the back side of the dial plate, and buckle is connected and fixed with the button in elastic wristband, connects elastic wristband and dial plate；
More physiology signal acquisition devices are fixed in elastic wristband.
Preferably, more physiology signal acquisition devices include ECG collection device and pulse collection device；The electrocardio
Acquisition device includes metal electrode and two conductive fabric electrodes, and two conductive fabric electrodes and metal electrode constitute electrocardiosignal
Three electrodes of acquisition；Described two conductive fabric electrodes are respectively embedded on the inside of elastic wristband, and the metal electrode is mounted on table
The back side of disk；The pulse collection device is embedded in case surface, using photoelectric sphyg blood oxygen transducer, receive respectively feux rouges and
Infrared light two-beam passes through the intensity of reflected light of subject's finger, and the acquisition of pulse wave is carried out using photoplethymograph, obtains two
The different pulse waveform in road；The output end of the ECG collection device and pulse collection device is all connected with transmitting device.
Preferably, the signal intelligent pretreatment unit includes first processing module and Second processing module；Described first
Processing module removes the insincere signal of low quality in more physiological signals；The Second processing module is to the height in more physiological signals
Quality trusted signal carries out signal processing；The Second processing module, including go baseline drift module, go Hz noise module and
Go High-frequency Interference module；It is described to go baseline drift module, baseline drift is removed to the high quality trusted signal in more physiological signals,
Obtain the physiological signal of removal baseline drift；It is described to go Hz noise module, more physiological signals of removal baseline drift are removed
Hz noise obtains the signal of removal Hz noise；It is described to go High-frequency Interference module, to more physiological signals of removal Hz noise
High-frequency noise interference is removed, the signal of removal high-frequency noise interference is obtained, as the input signal for carrying out feature extraction.
Preferably, the transmitting device is connect using radio receiving transmitting module with intelligent terminal, realizes more physiological signals
The real-time communication of acquisition device and intelligent terminal.
Preferably, the cardiovascular disease early warning system based on more physiological signal depth integrations further includes being arranged at table
Filter and a/d conversion device in disk；The filter and a/d conversion device are defeated with more physiology signal acquisition devices
Outlet is connected, and the output signal for more physiological acquisition devices is filtered and AD conversion, and more physiological signals after AD conversion are through nothing
Line transceiver module is transferred to intelligent terminal.
Preferably, the cardiovascular disease early warning system based on more physiological signal depth integrations further includes for filter
And a/d conversion device provides the power management module of reference voltage；The power management module includes electric power management circuit and electricity
Pond；Electric power management circuit realizes the safe charge and discharge of lithium battery using power management chip, and provides+3V burning voltage, pressure stabilizing core
+ 3V voltage is converted into+2.5V voltage by piece, is powered for filter and a/d conversion device and is provided stable reference voltage.
Preferably, the cardiovascular disease early warning system based on more physiological signal depth integrations further includes memory module；
The memory module selects the storage medium of large capacity, guarantees 24 hours above data of Coutinuous store, after storing AD conversion
More physiological signal original signals, calculate much physiological signal parameter and the Time-Frequency Analysis result of more physiological signals.
The beneficial effects of adopting the technical scheme are that provided by the invention a kind of deep based on more physiological signals
The cardiovascular disease early warning system of fusion is spent, adjustable wrist strap bandage is elastic, and equipment volume is small, the conductive fabric electrode used,
Material is soft, good with human skin stickiness, greatly reduces traditional equipment to the discomfort of skin, is equipment long periods of wear and monitoring
Provide great convenience with it is comfortable, and have compared with strong anti-interference ability, being capable of long-time stable measurement；It can the synchronous acquisition heart
The important physiological signal of the multichannels such as electricity, pulse, blood pressure.More physiological signal precision such as electrocardio, pulse, heart rate and professional equipment synchronize adopt
Collection compares, and can provide Diseases diagnosis foundation more acurrate, abundant, is wearable more physiologic signal monitoring dresses of a clinical grade
It sets.Compared with existing wearable device, the physiological signal that synchronous acquisition of the present invention arrives is more, accuracy is higher；And use two
Kind method carries out the early warning of cardiovascular disease risks, according to the Parameters of Time-frequency Field of a variety of physiological signals in intelligent terminal
Calculated result carries out real-time disease and diagnoses in advance；The disease intelligent method for classifying in server based on deep learning is to pendant beyond the clouds
More physiological signals of wearer carry out classification of diseases and diagnosis, and result is fed back to intelligent terminal, carry out risk of cardiovascular diseases
Early warning.More accurate reference is provided for the assessment of cardiac function and the diagnosis of heart disease.
Detailed description of the invention
Fig. 1 is a kind of cardiovascular disease early warning system based on more physiological signal depth integrations provided in an embodiment of the present invention
Structural block diagram；
Fig. 2 is the structural schematic diagram of wearable device provided in an embodiment of the present invention, wherein (a) is schematic perspective view,
It (b) is planar structure schematic diagram；
Fig. 3 is dial plate schematic perspective view provided in an embodiment of the present invention；
Fig. 4 is index dial structure schematic diagram provided in an embodiment of the present invention, wherein (a) is dial plate positive structure schematic,
It (b) is dial plate structure schematic diagram；
Fig. 5 is provided in an embodiment of the present invention using the cardiovascular disease of the invention based on more physiological signal depth integrations
Early warning system and device carry out the flow chart of risk of cardiovascular diseases early warning；
Fig. 6 is that cloud server provided in an embodiment of the present invention carries out disease intelligent classification to pretreated more physiological signals
Flow chart；
Fig. 7 is the structural block diagram of the depth analysis computing unit of more physiological signal fusions provided in an embodiment of the present invention.
In figure, 701, conductive fabric electrode；702, velcro；703, button；801, pulse collection device；802, metal electricity
Pole；Buckle 803.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
A kind of cardiovascular disease early warning system based on more physiological signal depth integrations, as shown in Figure 1, including wearing dress
It sets, more physiology signal acquisition devices, transmitting device, intelligent terminal and cloud server；Wearable device is worn on detected
Person's wrist portion, more physiology signal acquisition devices and transmitting device are arranged on wearable device；More physiology signal acquisition devices are used
In the physiological signal of acquisition detected person；The physiological signal data that transmitting device is used to acquire more physiology signal acquisition devices passes
It is defeated to arrive intelligent terminal；Intelligent terminal plug-in, for handling the physiological signal of detected person, judgement should
Whether detected person has a disease risks, carries out risk of cardiovascular diseases early warning, assists diagnosis, and by the physiological signal of processing
It is sent to cloud server；Cloud server plug-in, the disease intelligent method for classifying based on deep learning, according to having instructed
The kinds of Diseases practiced carry out classification of diseases and diagnosis to more physiological signals of wearer, and result is fed back to intelligent terminal；
Program built in intelligent terminal includes that signal intelligent pretreatment unit, feature extraction unit and parameter are calculated and analyzed
Unit and Risk-warning unit；Signal intelligent pretreatment unit realizes the more physiological signals acquired to more physiology signal acquisition devices
It is pre-processed, and pretreated more physiological signals is transferred to cloud server；Feature extraction unit is to by pretreated
The a variety of physiological signal waveforms of human body carry out feature point extraction；It includes that time domain parameter calculates and analysis mould that parameter, which is calculated with analytical unit,
Block and frequency domain parameter calculating and analysis module；Time domain parameter calculate and analysis module according to more physiological signal feature extractions as a result,
The time domain parameter for carrying out each physiological signal calculates and analysis；Frequency domain parameter calculates and analysis module is according to the time-frequencies of more physiological signals
It analyzes result and carries out frequency domain parameter calculating and analysis, the amplitude-frequency characteristic after seeking its Fourier transformation；Risk-warning unit is according to more
The real-time time-frequency domain analysis result of kind physiological signal parameter and the feedback result of cloud server, carry out disease risks early warning, auxiliary
Help diagnosis；
Program built in cloud server includes the depth analysis of multi-path time frequency analysis unit and the fusion of more physiological signals
Computing unit；Multi-path time frequency analysis unit includes time-domain analysis module and frequency-domain analysis module；Time-domain analysis module is to acquisition
To more physiological signal datas carry out respectively identical mapping and down-sampling transformation, obtain identical mapping after more physiological signal numbers
According to generating the time series sketch of different time scales, using down-sampling transformation thus to obtain multiple and different down-sampling rates
Input time sequence；Frequency-domain analysis module uses the low frequency filtering with multiple smoothnesses to collected more physiological signal datas
Device removes High-frequency Interference and random noise, and the rolling average of different windows is utilized according to different smoothnesses, obtains the defeated of multi-frequency
Angle of incidence sequence；The result that the depth analysis computing unit of more physiological signal fusions obtains multi-path time frequency analysis unit inputs
Convolution algorithm is carried out into convolutional neural networks；Information is carried out in full articulamentum or other classifiers to summarize, and obtains classification knot
Fruit；Finally, more physiological signal measurements data of wearer and the aspect ratio pair for training obtained different cardiovascular diseases are obtained
Risk of cardiovascular diseases classification results, and result is fed back into intelligent terminal.
A kind of cardiovascular disease early warning system based on more physiological signal depth integrations of the invention further includes being arranged at
Filter and a/d conversion device in dial plate；The output of filter and a/d conversion device with more physiology signal acquisition devices
End is connected, and the output signal for more physiological acquisition devices is filtered and AD conversion, and more physiological signals after AD conversion are through bluetooth
Radio receiving transmitting module is transferred to intelligent terminal.
A kind of cardiovascular disease early warning system based on more physiological signal depth integrations of the invention further includes for filtering dress
It sets and a/d conversion device provides the power management module and memory module of reference voltage；Power management module includes power management
Circuit and battery；Electric power management circuit realizes the safe charge and discharge of lithium battery using power management chip, and provides+3V and stablize electricity
+ 3V voltage is converted into+2.5V voltage by pressure, voltage stabilizing chip, is powered and is provided stable for filter and a/d conversion device
Reference voltage；Memory module selects the storage medium of large capacity, guarantees 24 hours above data of Coutinuous store, turns for storing AD
More physiological signal original signals after changing, calculate much Time-Frequency Analysis knots of physiological signal parameter and more physiological signals
Fruit.
Wearable device is as shown in Fig. 2, include elastic wristband, shell and dial plate；The elastic wristband by tender texture material
Material is made, and has comfort and scalability, adapts to different wrist sizes, elastic wristband bondage is in left hand wrist, elastic wristband
Outside middle position is two buttons 703；Dial plate is installed in the outside of elastic wristband, and elastic wristband both ends are for fixed elastic wrist
The velcro 702 of band, shell is installed on outside dial plate, index dial structure as shown in Figure 3 is formed, for encapsulating hardware circuit；Table
Buckle 803 is installed at the back side of disk, and buckle 803 is connected and fixed with the button 703 in elastic wristband, connects elastic wristband and table
Disk, the comfortableization for wearer is worn and signal acquisition steady in a long-term provides safeguard；More physiology signal acquisition devices are fixed on bullet
Property wrist strap on, can personalized adjustment bandage it is elastic, user wear for a long time will not generate sense of discomfort, wearing comfort height,
And have compared with strong anti-interference ability, can long-time stable measurement.
More physiology signal acquisition devices include ECG collection device and pulse collection device；ECG collection device includes metal
Electrode 802 and two conductive fabric electrodes 701, two conductive fabric electrodes 701 and metal electrode 802 constitute ecg signal acquiring
Three electrodes；Two conductive fabric electrodes 701 are respectively embedded on the inside of elastic wristband；As shown in figure 4, metal electrode 802 is installed
At the back side of dial plate；Pulse collection device is embedded in case surface, using photoelectric sphyg blood oxygen transducer, receive respectively feux rouges and
Infrared light two-beam passes through the intensity of reflected light of subject's finger, and the acquisition of pulse wave is carried out using photoplethymograph, obtains two
The different pulse waveform in road；The output end of ECG collection device and pulse collection device is all connected with transmitting device.When based on more
When the cardiovascular disease early warning system of physiological signal depth integration carries out disease risks early warning, the right hand of subject is being placed in dial plate just
Face, and a finger tip of the right hand is placed on pulse collection device 801, other fingers of the right hand are placed in ECG collection device metal electricity
On pole 802, synchronous acquisition multi-channal physiological may be implemented.The equipment volume is small, convenient to wear, with existing wearable device
It compares, obtained physiological parameter is more, can provide Diseases diagnosis foundation more acurrate, abundant, is truly realized precisely cardiovascular disease
Sick Risk-warning, auxiliary medical treatment.In terms of electrocardiosignal acquisition, using the letter of dry electrode (conductive fabric and metallic film)
Number acquisition sensor, different from usually used disposable electrode patch, dry electrode is reusable, avoids the wasting of resources.
Meanwhile conductive fabric is more soft, and it is good with human skin stickiness, greatly reduce traditional equipment to the discomfort of skin, to needs
The user being monitored for a long time bring great convenience with comfortably.
Signal intelligent pretreatment unit includes that first processing module and the removal of Second processing module first processing module are mostly raw
Manage the insincere signal of low quality in signal；Second processing module carries out signal to the high quality trusted signal in more physiological signals
Processing；Second processing module, including go baseline drift module, go Hz noise module and go High-frequency Interference module；Baseline is gone to float
Shifting formwork block removes baseline drift to the high quality trusted signal in more physiological signals, obtains the physiological signal of removal baseline drift；
Hz noise module is gone, Hz noise is removed to more physiological signals of removal baseline drift, obtains the signal of removal Hz noise；
High-frequency Interference module is gone, it is dry to obtain removal high-frequency noise for more physiological signals removal high-frequency noise interference to removal Hz noise
The signal disturbed, as the input signal for carrying out feature extraction.
Transmitting device is connect using radio receiving transmitting module with intelligent terminal, realizes more physiology signal acquisition devices and intelligence
The real-time communication of energy terminal device.
The present embodiment is by taking electrocardiosignal and pulse signal as an example, using of the invention based on more physiological signal depth integrations
Cardiovascular disease early warning system carries out risk of cardiovascular diseases early warning, as shown in Figure 5, comprising the following steps:
The a variety of physiological signals of human bodies such as step 1, more physiology signal acquisition devices acquisition electrocardiosignal, pulse wave signal, and
It is filtered by filter and a/d conversion device and AD conversion, more physiological signals after AD conversion are through being wirelessly transmitted to intelligence
Terminal device；
It is pre- that step 2, signal intelligent pretreatment unit carry out signal to more physiological signals (such as electrocardio, pulse wave) of acquisition
Processing, method particularly includes:
First processing module removes the insincere signal of low quality in more physiological signals (such as electrocardio, pulse)；Specifically,
By taking electrocardiosignal as an example, if the variation of electrocardiosignal amplitude is more than given threshold, electrocardiosignal is the insincere signal of low quality, no
Then judge baseline drift degree: if baseline drift degree is less than given threshold, electrocardiosignal is high quality trusted signal, no
Then electrocardiosignal is the insincere signal of low quality；
Second processing module carries out at signal the high quality trusted signal in more physiological signals (such as electrocardio, pulse)
Reason；Wherein, the more physiological signals for going baseline drift module to be greater than the set value using mean filter method to baseline drift degree are (such as
Electrocardio, pulse etc.) processing obtain baseline drift signal, using curve-fitting method to baseline drift degree be less than setting value life
Reason signal processing obtains baseline drift signal；After the baseline drift signal subtracted with original signal, the school of removal baseline drift is obtained
Positive signal.Hz noise module is gone, selects wavelet basis function to more physiological signals (such as electrocardio, pulse of removal baseline drift
Deng) decomposed；Fourier decomposition is carried out to each layer wavelet coefficient；Find frequency corresponding to the Hz noise of 50 to 60 hz
Wavelet coefficient, juxtaposition by its zero, other frequency wavelet coefficients remain unchanged；Small echo inversion is done according to current each wavelet coefficient
It changes, reconstruction signal is to get the physiological signal for arriving removal Hz noise.High-frequency Interference module is gone, according to making an uproar for a variety of physiological signals
Sound feature selects wavelet basis function to do multilevel wavelet decomposition transformation to the physiological signal of removal Hz noise；To each layer wavelet systems
Number does the processing of thresholding soft-threshold respectively, reduces the wavelet coefficient of high frequency section, removal high-frequency noise interference；To thresholding threshold process
Wavelet coefficient afterwards does wavelet inverse transformation, reconstructs physiological signal to get the physiological signal interfered to removal high-frequency noise.
Step 3, intelligent terminal and cloud server are respectively handled pretreated more physiological signals, specific method
Are as follows:
Intelligent terminal carries out processing to pretreated more physiological signals
Feature extraction unit carries out feature point extraction to more physiological signal waveforms of acquisition；
The present embodiment extracts QRS characteristic point by taking electrocardiosignal and pulse wave signal as an example, to electrocardiosignal, according to sampling frequency
Rate determines wavelet decomposition number of plies n, carries out n-layer wavelet decomposition using wavelet basis, extracts and reconstruct n-th layer high-frequency signal；
R wave of electrocardiosignal: given threshold is detected, guarantees threshold value under R wave wave crest, electrocardiosignal other parts are in threshold value
Under, the R wave that will be greater than threshold value at this time is found, and the real-time mark on electrocardiosignal；Detect electrocardiosignal Q wave: R wave wave crest
Abscissa move back one section of unit length, the cycle detection minimum point in this section, as Q wave, and mark；Detect electrocardio
Signal S wave: the abscissa of R wave wave crest to one section of unit length of Forward, cycle detection minimum point, as S in this section
Wave, and mark.It is similar to electrocardiosignal, multilevel wavelet decomposition is carried out with wavelet basis to pulse wave signal, extracts and reconstructs height
Frequency signal；Threshold value delimited, the wave crest beyond threshold value is main wave P in high-frequency signal, and the wave crest that threshold value is lower than in high-frequency signal is attached most importance to
Wave wave crest.
Parameter calculates and analytical unit carries out the calculating of real-time time-frequency field parameter to more physiological signals after feature extraction and divides
Analysis；
Time domain parameter calculate and analysis module according to (such as electrocardio, pulse wave) feature extraction of more physiological signals as a result, into
The time domain parameter of each physiological signal of row calculates and analysis；The present embodiment is by taking electrocardiosignal and pulse wave signal as an example.Calculate electrocardio
Signal parameter: RR interphase, QRS complex width, instantaneous heart rate, closest m RR interphase mean value, and carry out electrocardiosignal
HRV time-domain analysis；Pulse wave signal parameter: PP (main wave) interphase, real-time pressure value and blood oxygen saturation is calculated, and carries out pulse
The PRV time-domain analysis of wave；Finally, the stroke output that the hrv parameter and pulse wave signal that are calculated according to electrocardiosignal calculate is joined
Number, is calculated cardiac output per minute；
Frequency domain parameter calculate and analysis module according to the time frequency analysis results of more physiological signals (time frequency analysis of such as HRV,
The time frequency analysis etc. of PRV) carry out frequency domain parameter calculating and analysis, the amplitude-frequency characteristic after seeking its Fourier transformation.The present embodiment with
For electrocardiosignal and pulse wave signal, HRV spectrum analysis figure is calculated according to period parameters between electrocardiosignal RR；According to pulse
PRV spectrum analysis figure is calculated in period parameters between wave signal PP.
In the present embodiment, the time-domain analysis of HRV is carried out according to period parameters between electrocardiosignal RR, specially using continuously acquiring
To cardiac cycle of the RR interphase that is calculated of electro-cardiologic signal waveforms as electrocardiosignal.Description changes over time cardiac cycle
Relationship, find out its fitting function with interpolation method, reflect small the change of divergence between heart beat cycle, the as time-domain analysis of HRV；
The time-domain analysis of PRV is carried out according to period parameters between pulse wave signal PP, it is similar with HRV analysis, specially using continuously acquiring
The obtained PP interphase of pulse wave signal waveshape as cardiac cycle, the time-domain analysis of PRV can be obtained.
Real-time pressure value and blood oxygen saturation are calculated according to pulse wave signal；Real-time pressure value is calculated according to pulse wave signal
Specific method be main wave wave crest is carried out to pulse wave signal, weight wave wave crest carries out feature point extraction, and calculate the master of pulse wave
The characteristic parameters such as the wave rate of rise, systole phase and time diastole, estimate systolic pressure and diastolic blood pressure values, and real-time display.
Calculate blood oxygen saturation according to pulse wave signal method particularly includes: according to feux rouges and infrared light two-beam pass through by
The reflective light intensity and oxyhemoglobin of examination person's finger and hemoglobin are different to the degree of absorption that do not share the same light, with light splitting degree
Method measures the ratio of infrared light and red light absorption amount, calculates blood oxygen saturation.
Cloud server carries out disease intelligent classification to pretreated more physiological signals, as shown in Figure 6, comprising:
Time-domain analysis module to collected more physiological signal datas (such as electrocardio, pulse) carry out respectively identical mapping and
Down-sampling transformation, more physiological signal datas after obtaining identical mapping, generates different time scales using down-sampling transformation
Time series sketch, thus to obtain the input time sequence of multiple and different down-sampling rates.
Frequency-domain analysis module is multiple smooth using having to collected more physiological signal datas (such as electrocardio, pulse wave)
The low-frequency filter removal High-frequency Interference and random noise of degree, the rolling average of different windows is utilized according to different smoothnesses, is obtained
Obtain the input time sequence of multi-frequency.
The depth analysis computing unit of more physiological signal fusions, as shown in fig. 7, by 3 kinds of transformation data of acquisition: identical to reflect
The transformed multiple dimensioned time series of more physiological signals, down-sampling after penetrating and the multi-frequency time series after Spectrum Conversion are made
For the input of 3 convolutional neural networks in parallel, a kind of transformation data are input in a convolutional neural networks, each neural network
As feature learning tool, feature obtained by depth analysis is extracted using down-sampling.To be given after Data Integration full articulamentum or its
His classifier, classifies, and obtain classification accuracy.In the present embodiment, disease is carried out to arrhythmia cordis according to electrocardiosignal
Classification designs the convolutional neural networks of suitable parameter and depth, will containing normal heartbeat and arrhythmia cordis (bundle-branch block,
Atrial premature beats, ventricular premature beat etc.) electrocardiosignal training data, be divided into training set and the test of convolutional neural networks model
Collection randomly selects part sample as training set, remaining carries out Training as test set, is carried out using deep learning special
Sign learn simultaneously classify, when accuracy rate reaches it is expected when deconditioning, obtain classification results.According to pulse wave signal to artery sclerosis
Classification of diseases is carried out, design convolutional neural networks model carries out artery to normal pulse wave signal and artery sclerosis pulse wave signal
The classification based training of disease is hardened, classification results are obtained.Finally, classification of diseases and diagnostic result are fed back into intelligent terminal.
Step 4, intelligent terminal risk prewarning unit are according to a variety of real-time Time-Frequency Analysis of physiological signal parameter
As a result disease risks early warning is carried out with the classification results of cloud server；
In the present embodiment, according between the RR interphase of electrocardiosignal, QRS complex width, instantaneous heart rate, closest m RR
Phase mean value carries out risk of cardiovascular diseases early warning using following rule:
If (a) at least meeting one of following condition: 1) RR interphase is less than or equal to p times of (root of closest m RR interphase mean value
According to actual conditions, p desirable 0.8 or so)；2) QRS complex width is more than or equal to t seconds (for example settable t is 0.12 second or so),
Then carry out ventricular premature beat Risk-warning；
If (b) at least meeting one of following condition: 1) RR interphase is less than or equal between closest m (such as 5,7,9) a RR
P times of phase mean value；2) QRS complex width is less than t seconds, then carries out atrial premature beats Risk-warning；
If (c) at least meeting one of following condition: 1) p times of closest m RR interphase mean value is less than RR interphase；2) between RR
Phase is less than or equal to p times of (according to the actual situation, desirable 1.2 or so q) closest m RR interphase mean value；3) QRS complex width is big
In being equal to t seconds, then carries out the bundle-branch block heart and clap Risk-warning；
(d) in addition to the conditions already mentioned, it all carries out the sinus property heart and claps Risk-warning；
According to beat classification, Risk-warning further can be carried out to heart rate rhythm；
Sinus rhythm: being that Dou Xingxin is clapped；
Nodal tachycardia: three or more the sinus property hearts are clapped, and each heart claps heart rate and is greater than 120；
Sinus bradycardia: three or more the sinus property hearts are clapped, and each heart claps heart rate less than 50；
Sinus arrest: the RR interphase that two sinus property hearts are clapped is beyond certain time (generally taking RR interphase to be greater than 1.6 seconds)；
Fang Zao: one or more atrial premature beats；
Room is early: one or more ventricular premature beat；
Pairs of room is early: continuous two ventricular premature beat；
Bundle-branch block: continuous three and the above bundle-branch block heart are taken existing；
Ventricular premature beat bigeminy: each sinus property heart is clapped followed by a ventricular premature beat, and is at least repeated three times；
Ventricular premature beat trigeminy: the every two sinus property heart clap followed by a ventricular premature beat or each sinus property heart clap followed by
Two ventricular premature beat, and be at least repeated twice；
Atrial tachycardia: three and the continuous appearance of above atrial premature beats heart bat, and each bat heart rate is greater than 120；
Ventricular Tachycardia: three and the continuous appearance of above ventricular premature beat heart bat, and each bat heart rate is greater than 120.
According to the real-time pressure value and blood oxygen saturation of pulse wave signal, disease risks early warning is carried out: when real-time pressure value
The continuous n sampling instant of blood oxygen saturation beyond setting normal arterial pressure range or setting normal blood oxygen saturation when, into
The early warning of row dysarteriotony or blood oxygen saturation abnormity early warning.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify to technical solution documented by previous embodiment, or some or all of the technical features are equal
Replacement；And these are modified or replaceed, model defined by the claims in the present invention that it does not separate the essence of the corresponding technical solution
It encloses.
Claims (8)
1. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations, it is characterised in that: including wearable device,
More physiology signal acquisition devices, transmitting device, intelligent terminal and cloud server；The wearable device is worn on detected
Person's wrist portion, more physiology signal acquisition devices and transmitting device are arranged on wearable device；More physiological signals are adopted
Acquisition means are used to acquire the physiological signal of detected person；The transmitting device is used for the life for acquiring more physiology signal acquisition devices
Reason signal data is transferred to intelligent terminal；The intelligent terminal plug-in, for believing the physiology of detected person
It number is handled, judges whether the detected person has risk of cardiovascular diseases, carried out disease risks early warning, assist diagnosis,
And the physiological signal of processing is sent to cloud server；The cloud server plug-in, the disease based on deep learning
Intelligent method for classifying carries out classification of diseases and diagnosis according to more physiological signals of the kinds of Diseases of trained mistake to wearer,
And result is fed back into intelligent terminal；
Program built in the intelligent terminal includes that signal intelligent pretreatment unit, feature extraction unit and parameter are calculated and analyzed
Unit and Risk-warning unit；The signal intelligent pretreatment unit realizes the more physiology acquired to more physiology signal acquisition devices
Signal is pre-processed, and pretreated more physiological signals are transferred to cloud server；The feature extraction unit is to process
The pretreated a variety of physiological signal waveforms of human body carry out feature point extraction；It includes time domain parameter that the parameter, which is calculated with analytical unit,
It calculates and analysis module and frequency domain parameter calculating and analysis module；The time domain parameter calculates and analysis module is believed according to more physiology
Number feature extraction is as a result, the time domain parameter for carrying out each physiological signal calculates and analysis；The frequency domain parameter calculates and analysis module
It carries out frequency domain parameter according to the time frequency analysis result of more physiological signals to calculate and analyze, the amplitude-frequency after seeking its Fourier transformation is special
Property；The Risk-warning unit is according to the real-time time-frequency domain analysis result of a variety of physiological signal parameters and the feedback of cloud server
As a result, carrying out disease risks early warning, diagnosis is assisted；
Program built in the cloud server includes the depth analysis of multi-path time frequency analysis unit and the fusion of more physiological signals
Computing unit；The multi-path time frequency analysis unit includes time-domain analysis module and frequency-domain analysis module；The time-domain analysis mould
Block carries out identical mapping respectively to collected more physiological signal datas and down-sampling converts, more physiology after obtaining identical mapping
Signal data generates the time series sketch of different time scales using down-sampling transformation, thus to obtain adopting under multiple and different
The input time sequence of sample rate；The frequency-domain analysis module, which uses collected more physiological signal datas, has multiple smoothnesses
Low-frequency filter removal High-frequency Interference and random noise, the rolling average of different windows is utilized according to different smoothnesses, is obtained
The input time sequence of multi-frequency；The depth analysis computing unit of the more physiological signals fusion is by multi-path time frequency analysis unit
The result of acquisition, which is input in convolutional neural networks, carries out convolution algorithm；Information remittance is carried out in full articulamentum or other classifiers
Always, classification results are obtained；Finally, by more physiological signal measurements data of wearer and trained obtained different cardiovascular diseases
Aspect ratio pair obtains risk of cardiovascular diseases classification results, and result is fed back to intelligent terminal.
2. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the wearable device includes elastic wristband, shell and dial plate；The elastic wristband is made of the material of tender texture,
Middle position is two buttons on the outside of elastic wristband；Dial plate is installed in the outside of elastic wristband, and elastic wristband both ends are for fixing
The velcro of elastic wristband；The shell is installed on outside dial plate, index dial structure is formed, for encapsulating hardware circuit；The table
Buckle is installed at the back side of disk, and buckle is connected and fixed with the button in elastic wristband, connects elastic wristband and dial plate；It is described more
Physiology signal acquisition device is fixed in elastic wristband.
3. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: more physiology signal acquisition devices include ECG collection device and pulse collection device；The ECG collection device
Including metal electrode and two conductive fabric electrodes, two conductive fabric electrodes and metal electrode constitute the three of ecg signal acquiring
A electrode；Described two conductive fabric electrodes are respectively embedded on the inside of elastic wristband, and the metal electrode is mounted on the back side of dial plate；
The pulse collection device is embedded in case surface, using photoelectric sphyg blood oxygen transducer, receives feux rouges and infrared light two respectively
Shu Guang passes through the intensity of reflected light of subject's finger, and the acquisition of pulse wave is carried out using photoplethymograph, it is different to obtain two-way
Pulse waveform；The output end of the ECG collection device and pulse collection device is all connected with transmitting device.
4. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the signal intelligent pretreatment unit includes first processing module and Second processing module；The first processing module
Remove the insincere signal of low quality in more physiological signals；The Second processing module is credible to the high quality in more physiological signals
Signal carries out signal processing；The Second processing module, including go baseline drift module, go Hz noise module and go high frequency dry
Disturb module；It is described to go baseline drift module, baseline drift is removed to the high quality trusted signal in more physiological signals, is removed
The physiological signal of baseline drift；It is described to go Hz noise module, Hz noise is removed to more physiological signals of removal baseline drift,
Obtain the signal of removal Hz noise；It is described to go High-frequency Interference module, high frequency is removed to more physiological signals of removal Hz noise
Noise jamming obtains the signal of removal high-frequency noise interference, as the input signal for carrying out feature extraction.
5. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the transmitting device is connect using radio receiving transmitting module with intelligent terminal, realizes more physiology signal acquisition devices
With the real-time communication of intelligent terminal.
6. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the cardiovascular disease early warning system based on more physiological signal depth integrations further includes the filter being arranged in dial plate
Wave apparatus and a/d conversion device；The filter and a/d conversion device with the output end phase of more physiology signal acquisition devices
Connect, the output signal for more physiological acquisition devices is filtered and AD conversion, and more physiological signals after AD conversion are through wireless receiving and dispatching
Module transfer is to intelligent terminal.
7. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the cardiovascular disease early warning system based on more physiological signal depth integrations further includes turning for filter and AD
The power management module of changing device offer reference voltage；The power management module includes electric power management circuit and battery；Power supply
It manages circuit and the safe charge and discharge of lithium battery is realized using power management chip, and provide+3V burning voltage, voltage stabilizing chip is by+3V
Voltage is converted into+2.5V voltage, powers for filter and a/d conversion device and provides stable reference voltage.
8. a kind of cardiovascular disease early warning system based on more physiological signal depth integrations according to claim 1, special
Sign is: the cardiovascular disease early warning system based on more physiological signal depth integrations further includes memory module；The storage
Module selects the storage medium of large capacity, guarantees 24 hours above data of Coutinuous store, for storing more physiology after AD conversion
Signal original signal, calculate much physiological signal parameter and the Time-Frequency Analysis result of more physiological signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811085130.4A CN109157202B (en) | 2018-09-18 | 2018-09-18 | Cardiovascular disease early warning system based on multi-physiological signal deep fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811085130.4A CN109157202B (en) | 2018-09-18 | 2018-09-18 | Cardiovascular disease early warning system based on multi-physiological signal deep fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109157202A true CN109157202A (en) | 2019-01-08 |
| CN109157202B CN109157202B (en) | 2021-06-01 |
Family
ID=64879608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811085130.4A Active CN109157202B (en) | 2018-09-18 | 2018-09-18 | Cardiovascular disease early warning system based on multi-physiological signal deep fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109157202B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109645963A (en) * | 2019-02-25 | 2019-04-19 | 深圳奥思顿健康科技有限公司 | It is a kind of for detecting the intelligent analysis system of vital sign and diagnosis by feeling the pulse |
| CN110037668A (en) * | 2019-04-10 | 2019-07-23 | 常熟理工学院 | The system that pulse signal time-space domain binding model judges age, health status and malignant arrhythmia identification |
| CN110192842A (en) * | 2019-05-30 | 2019-09-03 | 华南理工大学 | System and method is monitored based on the integrated data of physiological index of cloud side end |
| CN110200621A (en) * | 2019-06-06 | 2019-09-06 | 中山大学孙逸仙纪念医院 | A kind of cardiovascular event early warning analysis method |
| CN110236906A (en) * | 2019-05-20 | 2019-09-17 | 安徽通灵仿生科技有限公司 | A kind of reaction type multi-modal data fusion synchronization accessory heart control system |
| CN110584599A (en) * | 2019-08-07 | 2019-12-20 | 王满 | Wavelet transformation data processing system and method based on cardiac function dynamic monitoring |
| CN111248877A (en) * | 2020-04-18 | 2020-06-09 | 赵宏杰 | Myocardial infarction early warning system |
| CN111419214A (en) * | 2020-03-31 | 2020-07-17 | 联想(北京)有限公司 | Electrocardio abnormality detection method, terminal and server |
| CN111839480A (en) * | 2020-07-14 | 2020-10-30 | 广州智康云科技有限公司 | Robot detection processing system and method and robot |
| CN111956215A (en) * | 2020-07-29 | 2020-11-20 | 鲁东大学 | QRS point detection method of low-quality electrocardiogram |
| CN112263249A (en) * | 2019-07-08 | 2021-01-26 | 复旦大学附属中山医院 | ECG-based method and device for enhancing blood oxygen saturation monitoring |
| CN112505798A (en) * | 2020-11-27 | 2021-03-16 | 河北雄安太芯电子科技有限公司 | Object detection method based on terahertz |
| CN112657050A (en) * | 2020-12-01 | 2021-04-16 | 北京工业大学 | Artificial heart control system based on Internet of things edge calculation and operation method |
| CN113876308A (en) * | 2021-11-02 | 2022-01-04 | 南华大学 | Intelligent internet-of-things cardiovascular disease medical health early warning system |
| CN113892926A (en) * | 2021-09-08 | 2022-01-07 | 杭州回车电子科技有限公司 | Heart rate signal processing method and device based on head pulse wave and electronic device |
| CN114072047A (en) * | 2021-08-18 | 2022-02-18 | 中国人民解放军总医院第二医学中心 | Multi-physiological-parameter detection glove and hypertension disease risk detection system |
| WO2022041225A1 (en) * | 2020-08-31 | 2022-03-03 | 中山大学 | Server for use in assessing cardiovascular state, wearable device, and method for cardiovascular state assessment |
| CN114224348A (en) * | 2021-11-29 | 2022-03-25 | 江南大学 | Combined neural network electrocardiogram classification method and system |
| US11540762B2 (en) | 2014-10-30 | 2023-01-03 | West Affum Holdings Dac | Wearable cardioverter defibrtillator with improved ECG electrodes |
| US11745006B2 (en) | 2014-10-30 | 2023-09-05 | West Affum Holdings Dac | Wearable cardiac defibrillation system with electrode assemblies having pillow structure |
| CN117224092A (en) * | 2023-11-16 | 2023-12-15 | 常熟理工学院 | Photoelectric volume pulse wave interference band real-time detection method and system based on decision tree |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002165768A (en) * | 2000-12-04 | 2002-06-11 | Casio Comput Co Ltd | Measurement device to be set on the arm |
| CN101264011A (en) * | 2007-03-12 | 2008-09-17 | 三星电子株式会社 | Method and apparatus for cufflessly and non-invasively measuring wrist blood pressure |
| EP2542147A2 (en) * | 2010-03-04 | 2013-01-09 | Neumitra LLC | Devices and methods for treating psychological disorders |
| CN103284702A (en) * | 2013-06-17 | 2013-09-11 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram and pulse wave relation analysis method and method and device of fusion analysis |
| CN204009405U (en) * | 2014-09-04 | 2014-12-10 | 康泰医学系统（秦皇岛）股份有限公司 | The intelligent watch of collection passometer, electrocardio, blood-oxygen functional |
| CN104545844A (en) * | 2014-12-25 | 2015-04-29 | 中国科学院苏州生物医学工程技术研究所 | Multi-parameter sleep monitoring and intelligent diagnosis system based on 4G mobile communication technology and application method of multi-parameter sleep monitoring and intelligent diagnosis system |
| CN104706349A (en) * | 2015-04-13 | 2015-06-17 | 大连理工大学 | Electrocardiosignal construction method based on pulse wave signals |
| CN105708441A (en) * | 2014-12-03 | 2016-06-29 | 中国科学院苏州纳米技术与纳米仿生研究所 | Wearable finger stall and electrocardiogram and pulse condition acquisition terminal |
| CN106066933A (en) * | 2016-05-27 | 2016-11-02 | 成都信汇聚源科技有限公司 | The method obtaining atrial fibrillation identification artificial neural network weighted value matrix |
| CN107334466A (en) * | 2017-08-08 | 2017-11-10 | 西安交通大学 | A kind of apparatus and method of wearable chronic disease intelligent monitoring and early warning |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
-
2018
- 2018-09-18 CN CN201811085130.4A patent/CN109157202B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002165768A (en) * | 2000-12-04 | 2002-06-11 | Casio Comput Co Ltd | Measurement device to be set on the arm |
| CN101264011A (en) * | 2007-03-12 | 2008-09-17 | 三星电子株式会社 | Method and apparatus for cufflessly and non-invasively measuring wrist blood pressure |
| EP2542147A2 (en) * | 2010-03-04 | 2013-01-09 | Neumitra LLC | Devices and methods for treating psychological disorders |
| CN103284702A (en) * | 2013-06-17 | 2013-09-11 | 中国科学院苏州纳米技术与纳米仿生研究所 | Electrocardiogram and pulse wave relation analysis method and method and device of fusion analysis |
| CN204009405U (en) * | 2014-09-04 | 2014-12-10 | 康泰医学系统（秦皇岛）股份有限公司 | The intelligent watch of collection passometer, electrocardio, blood-oxygen functional |
| CN105708441A (en) * | 2014-12-03 | 2016-06-29 | 中国科学院苏州纳米技术与纳米仿生研究所 | Wearable finger stall and electrocardiogram and pulse condition acquisition terminal |
| CN104545844A (en) * | 2014-12-25 | 2015-04-29 | 中国科学院苏州生物医学工程技术研究所 | Multi-parameter sleep monitoring and intelligent diagnosis system based on 4G mobile communication technology and application method of multi-parameter sleep monitoring and intelligent diagnosis system |
| CN104706349A (en) * | 2015-04-13 | 2015-06-17 | 大连理工大学 | Electrocardiosignal construction method based on pulse wave signals |
| CN106066933A (en) * | 2016-05-27 | 2016-11-02 | 成都信汇聚源科技有限公司 | The method obtaining atrial fibrillation identification artificial neural network weighted value matrix |
| CN107334466A (en) * | 2017-08-08 | 2017-11-10 | 西安交通大学 | A kind of apparatus and method of wearable chronic disease intelligent monitoring and early warning |
| CN107510452A (en) * | 2017-09-30 | 2017-12-26 | 扬美慧普（北京）科技有限公司 | A kind of ECG detecting method based on multiple dimensioned deep learning neutral net |
Non-Patent Citations (1)
| Title |
|---|
| 徐礼胜: "多传感器融合的穿戴式心率监测系统", 《哈尔滨工业大学学报》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11540762B2 (en) | 2014-10-30 | 2023-01-03 | West Affum Holdings Dac | Wearable cardioverter defibrtillator with improved ECG electrodes |
| US11745006B2 (en) | 2014-10-30 | 2023-09-05 | West Affum Holdings Dac | Wearable cardiac defibrillation system with electrode assemblies having pillow structure |
| CN109645963A (en) * | 2019-02-25 | 2019-04-19 | 深圳奥思顿健康科技有限公司 | It is a kind of for detecting the intelligent analysis system of vital sign and diagnosis by feeling the pulse |
| CN110037668A (en) * | 2019-04-10 | 2019-07-23 | 常熟理工学院 | The system that pulse signal time-space domain binding model judges age, health status and malignant arrhythmia identification |
| CN110037668B (en) * | 2019-04-10 | 2022-02-01 | 常熟理工学院 | System for judging age, health state and malignant arrhythmia identification by combining pulse signal time-space domain with model |
| CN110236906A (en) * | 2019-05-20 | 2019-09-17 | 安徽通灵仿生科技有限公司 | A kind of reaction type multi-modal data fusion synchronization accessory heart control system |
| CN110192842A (en) * | 2019-05-30 | 2019-09-03 | 华南理工大学 | System and method is monitored based on the integrated data of physiological index of cloud side end |
| CN110200621A (en) * | 2019-06-06 | 2019-09-06 | 中山大学孙逸仙纪念医院 | A kind of cardiovascular event early warning analysis method |
| CN112263249A (en) * | 2019-07-08 | 2021-01-26 | 复旦大学附属中山医院 | ECG-based method and device for enhancing blood oxygen saturation monitoring |
| CN110584599A (en) * | 2019-08-07 | 2019-12-20 | 王满 | Wavelet transformation data processing system and method based on cardiac function dynamic monitoring |
| CN111419214A (en) * | 2020-03-31 | 2020-07-17 | 联想(北京)有限公司 | Electrocardio abnormality detection method, terminal and server |
| CN111248877A (en) * | 2020-04-18 | 2020-06-09 | 赵宏杰 | Myocardial infarction early warning system |
| CN111839480A (en) * | 2020-07-14 | 2020-10-30 | 广州智康云科技有限公司 | Robot detection processing system and method and robot |
| CN111839480B (en) * | 2020-07-14 | 2024-03-29 | 广州智康云科技有限公司 | Detection processing system and method of robot and robot |
| CN111956215A (en) * | 2020-07-29 | 2020-11-20 | 鲁东大学 | QRS point detection method of low-quality electrocardiogram |
| WO2022041225A1 (en) * | 2020-08-31 | 2022-03-03 | 中山大学 | Server for use in assessing cardiovascular state, wearable device, and method for cardiovascular state assessment |
| CN112505798A (en) * | 2020-11-27 | 2021-03-16 | 河北雄安太芯电子科技有限公司 | Object detection method based on terahertz |
| CN112505798B (en) * | 2020-11-27 | 2022-07-01 | 河北雄安太芯电子科技有限公司 | Object detection method based on terahertz |
| CN112657050A (en) * | 2020-12-01 | 2021-04-16 | 北京工业大学 | Artificial heart control system based on Internet of things edge calculation and operation method |
| CN114072047A (en) * | 2021-08-18 | 2022-02-18 | 中国人民解放军总医院第二医学中心 | Multi-physiological-parameter detection glove and hypertension disease risk detection system |
| CN113892926A (en) * | 2021-09-08 | 2022-01-07 | 杭州回车电子科技有限公司 | Heart rate signal processing method and device based on head pulse wave and electronic device |
| CN113876308A (en) * | 2021-11-02 | 2022-01-04 | 南华大学 | Intelligent internet-of-things cardiovascular disease medical health early warning system |
| CN114224348A (en) * | 2021-11-29 | 2022-03-25 | 江南大学 | Combined neural network electrocardiogram classification method and system |
| CN117224092A (en) * | 2023-11-16 | 2023-12-15 | 常熟理工学院 | Photoelectric volume pulse wave interference band real-time detection method and system based on decision tree |
| CN117224092B (en) * | 2023-11-16 | 2024-02-09 | 常熟理工学院 | Photoelectric volume pulse wave interference band real-time detection method and system based on decision tree |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109157202B (en) | 2021-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109157202A (en) | A kind of cardiovascular disease early warning system based on more physiological signal depth integrations | |
| KR101084554B1 (en) | Method and apparatus for measuring heart related parameters | |
| CN108478203A (en) | A kind of blood pressure measuring method monitoring radar based on single vital sign | |
| CN110236508A (en) | A kind of non-invasive blood pressure continuous monitoring method | |
| WO2022246987A1 (en) | Construction method and application of hemodynamics-based digital human cardiovascular system | |
| CN103830844A (en) | Infrared liver vital energy function blood flow conditioning instrument modulated through low-frequency electromagnetic vibration | |
| Sel et al. | ImpediBands: Body coupled bio-impedance patches for physiological sensing proof of concept | |
| Hafid et al. | Simultaneous recording of ICG and ECG using Z-RPI device with minimum number of electrodes | |
| Dubey et al. | Respire: A spectral kurtosis-based method to extract respiration rate from wearable ppg signals | |
| CN114648040A (en) | Method for extracting and fusing multiple physiological signals of vital signs | |
| CN113040738B (en) | Blood pressure detecting device | |
| Iskandar et al. | A wearable 1-lead necklace ECG for continuous heart rate monitoring | |
| von Rosenberg et al. | Smart helmet: monitoring brain, cardiac and respiratory activity | |
| Hu et al. | A wearable device for collecting multi-signal parameters of newborn | |
| Paket et al. | ECG Monitoring System Using Textile Electrodes | |
| JP2024516573A (en) | Physiological parameter sensing system and method - Patents.com | |
| Anisimov et al. | Comparison of heart rate derived from ECG and pulse wave signals during controlled breathing test for biofeedback systems | |
| CN114903445A (en) | Intelligent monitoring and early warning system for cardiovascular and cerebrovascular diseases | |
| CN209733969U (en) | Pulse wave propagation time measuring equipment | |
| Agham et al. | An Unsupervised Learning of Impedance Plethysmograph for Perceiving Cardiac Events:(Unsupervised Learning of Impedance Plethysmograph) | |
| KH et al. | Wearable ECG electrodes for detection of heart rate and arrhythmia classification | |
| Yılmaz et al. | Comparison of Electrode Configurations for Impedance Plethysmography Based Heart Rate Estimation at the Forearm | |
| Gbaoui et al. | Decomposition of photoplethysmographical arterial pulse waves by independent component analysis: possibilities and limitations | |
| Cippitelli | Arrhythmia Detection based on Photoplethysmography | |
| GB2574293A (en) | Heart condition monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |